Neural network models are structured as a series of layers that reflect the way the brain processes information. The neural network classifiers available in Statistics and Machine Learning Toolbox™ are fully connected, feedforward neural networks for which you can adjust the size of the fully connected layers and change the activation functions of the layers.
To train a neural network classification model, use the Classification Learner app. For greater flexibility, train a neural network classifier using
fitcnet in the command-line interface. After training, you can classify new data by passing the model and the new predictor data to
If you want to create more complex deep learning networks and have Deep Learning Toolbox™, you can try the Deep Network Designer (Deep Learning Toolbox) app.
|Classification Learner||Train models to classify data using supervised machine learning|
|ClassificationNeuralNetwork Predict||Classify observations using neural network classification model (Since R2021b)|
Create Neural Network Model
|Cross-validate machine learning model|
|Classification loss for cross-validated classification model|
|Classify observations in cross-validated classification model|
|Classification edge for cross-validated classification model|
|Classification margins for cross-validated classification model|
|Cross-validate function for classification|
|Classification loss for neural network classifier (Since R2021a)|
|Resubstitution classification loss|
|Classification edge for neural network classifier (Since R2021a)|
|Classification margins for neural network classifier (Since R2021a)|
|Resubstitution classification edge|
|Resubstitution classification margin|
- Assess Neural Network Classifier Performance
fitcnetto create a feedforward neural network classifier with fully connected layers, and assess the performance of the model on test data.
- Train Neural Network Classifiers Using Classification Learner App
Create and compare neural network classifiers, and export trained models to make predictions for new data.
- Compress Machine Learning Model for Memory-Limited Hardware
Reduce model size by feature selection, constrained Bayesian optimization, and parameter quantization.